# Out-of-Distribution Detection using Multiple Semantic Label Representations

arXiv: https://arxiv.org/abs/1808.06664 · HTML: https://mlsanity.com/paper/1808.06664/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2018.

## Built on by (most cited first, 22 of 22)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [A framework for benchmarking class-out-of-distribution detection and its application to ImageNet](https://mlsanity.com/paper/2302.11893/) (2023)
- [Igeood: An Information Geometry Approach to Out-of-Distribution Detection](https://mlsanity.com/paper/2203.07798/) (2022)
- [RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection](https://mlsanity.com/paper/2204.02553/) (2022)
- [Out-of-distribution Detection with Boundary Aware Learning](https://mlsanity.com/paper/2112.11648/) (2021)
- [Revealing the Distributional Vulnerability of Discriminators by Implicit Generators](https://mlsanity.com/paper/2108.09976/) (2021)
- [A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2307.15252/) (2023)
- [Dual Representation Learning for Out-of-Distribution Detection](https://mlsanity.com/paper/2206.09387/) (2022)
- [A Baseline for Detecting Out-of-Distribution Examples in Image Captioning](https://mlsanity.com/paper/2207.05418/) (2022)
- [Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling](https://mlsanity.com/paper/2201.06378/) (2022)
- [TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring](https://mlsanity.com/paper/2207.11290/) (2022)
- [Evaluation of autonomous systems under data distribution shifts](https://mlsanity.com/paper/2406.20046/) (2024)
- [Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Tasks](https://mlsanity.com/paper/2205.09021/) (2022)
- [Which models are innately best at uncertainty estimation?](https://mlsanity.com/paper/2206.02152/) (2022)
- [Collaborative Knowledge Distillation via a Learning-by-Education Node Community](https://mlsanity.com/paper/2410.00074/) (2024)
- [On the Importance of Regularisation & Auxiliary Information in OOD Detection](https://mlsanity.com/paper/2107.07564/) (2021)
- [Wakeword Detection under Distribution Shifts](https://mlsanity.com/paper/2207.06423/) (2022)
- [Provably Uncertainty-Guided Universal Domain Adaptation](https://mlsanity.com/paper/2209.09616/) (2022)
- [Interactive System-wise Anomaly Detection](https://mlsanity.com/paper/2304.10704/) (2023)
- [Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection](https://mlsanity.com/paper/2605.20502/) (2026)

## Abstract (arXiv)

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how a network will act when it is fed with an out-of-distribution example. In this work, we consider the problem of out-of-distribution detection in neural networks. We propose to use multiple semantic dense representations instead of sparse representation as the target label. Specifically, we propose to use several word representations obtained from different corpora or architectures as target labels. We evaluated the proposed model on computer vision, and speech commands detection tasks and compared it to previous methods. Results suggest that our method compares favorably with previous work. Besides, we present the efficiency of our approach for detecting wrongly classified and adversarial examples.